Biosynthesis of rare 20(R)-protopanaxadiol/protopanaxatriol type ginsenosides through Escherichia coli engineered with uridine diphosphate glycosyltransferase genes

Yu, Lu,Chen, Yuan,Shi, Jie,Wang, Rufeng,Yang, Yingbo,Yang, Li,Zhao, Shujuan,Wang, Zhengtao The Korean Society of Ginseng 2019 Journal of Ginseng Research Vol.43 No.1

Background: Ginsenosides are known as the principal pharmacological active constituents in Panax medicinal plants such as Asian ginseng, American ginseng, and Notoginseng. Some ginsenosides, especially the 20(R) isomers, are found in trace amounts in natural sources and are difficult to chemically synthesize. The present study provides an approach to produce such trace ginsenosides applying biotransformation through Escherichia coli modified with relevant genes. Methods: Seven uridine diphosphate glycosyltransferase (UGT) genes originating from Panax notoginseng, Medicago sativa, and Bacillus subtilis were synthesized or cloned and constructed into pETM6, an ePathBrick vector, which were then introduced into E. coli BL21star (DE3) separately. 20(R)-Protopanaxadiol (PPD), 20(R)-protopanaxatriol (PPT), and 20(R)-type ginsenosides were used as substrates for biotransformation with recombinant E. coli modified with those UGT genes. Results: E. coli engineered with $GT95^{syn}$ selectively transfers a glucose moiety to the C20 hydroxyl of 20(R)-PPD and 20(R)-PPT to produce 20(R)-CK and 20(R)-F1, respectively. GTK1- and GTC1-modified E. coli glycosylated the C3-OH of 20(R)-PPD to form 20(R)-Rh2. Moreover, E. coli containing $p2GT95^{syn}K1$, a recreated two-step glycosylation pathway via the ePathBrich, implemented the successive glycosylation at C20-OH and C3-OH of 20(R)-PPD and yielded 20(R)-F2 in the biotransformation broth. Conclusion: This study demonstrates that rare 20(R)-ginsenosides can be produced through E. coli engineered with UTG genes.

Summarizing the Differences in Chinese-Vietnamese Bilingual News

Jinjuan Wu,Zhengtao Yu,Shulong Liu,Yafei Zhang,Shengxiang Gao 한국정보처리학회 2019 Journal of information processing systems Vol.15 No.6

Summarizing the differences in Chinese-Vietnamese bilingual news plays an important supporting role in thecomparative analysis of news views between China and Vietnam. Aiming at cross-language problems in theanalysis of the differences between Chinese and Vietnamese bilingual news, we propose a new method ofsummarizing the differences based on an undirected graph model. The method extracts elements to representthe sentences, and builds a bridge between different languages based on Wikipedia’s multilingual conceptdescription page. Firstly, we calculate the similarity between Chinese and Vietnamese news sentences, andfilter the bilingual sentences accordingly. Then we use the filtered sentences as nodes and the similarity gradeas the weight of the edge to construct an undirected graph model. Finally, combining the random walkalgorithm, the weight of the node is calculated according to the weight of the edge, and sentences with highestweight can be extracted as the difference summary. The experiment results show that our proposed approachachieved the highest score of 0.1837 on the annotated test set, which outperforms the state-of-the-artsummarization models.

Summarizing the Differences in Chinese-Vietnamese Bilingual News

Wu, Jinjuan,Yu, Zhengtao,Liu, Shulong,Zhang, Yafei,Gao, Shengxiang Korea Information Processing Society 2019 Journal of information processing systems Vol.15 No.6

Summarizing the differences in Chinese-Vietnamese bilingual news plays an important supporting role in the comparative analysis of news views between China and Vietnam. Aiming at cross-language problems in the analysis of the differences between Chinese and Vietnamese bilingual news, we propose a new method of summarizing the differences based on an undirected graph model. The method extracts elements to represent the sentences, and builds a bridge between different languages based on Wikipedia's multilingual concept description page. Firstly, we calculate the similarity between Chinese and Vietnamese news sentences, and filter the bilingual sentences accordingly. Then we use the filtered sentences as nodes and the similarity grade as the weight of the edge to construct an undirected graph model. Finally, combining the random walk algorithm, the weight of the node is calculated according to the weight of the edge, and sentences with highest weight can be extracted as the difference summary. The experiment results show that our proposed approach achieved the highest score of 0.1837 on the annotated test set, which outperforms the state-of-the-art summarization models.

Case-Related News Filtering via Topic-Enhanced Positive-Unlabeled Learning

Guanwen Wang,Zhengtao Yu,Yantuan Xian,Yu Zhang 한국정보처리학회 2021 Journal of information processing systems Vol.17 No.6

Case-related news filtering is crucial in legal text mining and divides news into case-related and case-unrelated categories. Because case-related news originates from various fields and has different writing styles, it is difficult to establish complete filtering rules or keywords for data collection. In addition, the labeled corpus for case-related news is sparse; therefore, to train a high-performance classification model, it is necessary to annotate the corpus. To address this challenge, we propose topic-enhanced positive-unlabeled learning, which selects positive and negative samples guided by topics. Specifically, a topic model based on a variational autoencoder (VAE) is trained to extract topics from unlabeled samples. By using these topics in the iterative process of positive-unlabeled (PU) learning, the accuracy of identifying case-related news can be improved. From the experimental results, it can be observed that the F1 value of our method on the test set is 1.8% higher than that of the PU learning baseline model. In addition, our method is more robust with low initial samples and high iterations, and compared with advanced PU learning baselines such as nnPU and I-PU, we obtain a 1.1% higher F1 value, which indicates that our method can effectively identify case-related news.

A Method of Chinese and Thai Cross-Lingual Query Expansion Based on Comparable Corpus

Tang, Peili,Zhao, Jing,Yu, Zhengtao,Wang, Zhuo,Xian, Yantuan Korea Information Processing Society 2017 Journal of information processing systems Vol.13 No.4

Cross-lingual query expansion is usually based on the relationship among monolingual words. Bilingual comparable corpus contains relationships among bilingual words. Therefore, this paper proposes a method based on these relationships to conduct query expansion. First, the word vectors which characterize the bilingual words are trained using Chinese and Thai bilingual comparable corpus. Then, the correlation between Chinese query words and Thai words are computed based on these word vectors, followed with selecting the Thai candidate expansion terms via the correlative value. Then, multi-group Thai query expansion sentences are built by the Thai candidate expansion words based on Chinese query sentence. Finally, we can get the optimal sentence using the Chinese and Thai query expansion method, and perform the Thai query expansion. Experiment results show that the cross-lingual query expansion method we proposed can effectively improve the accuracy of Chinese and Thai cross-language information retrieval.

Burmese Sentiment Analysis Based on Transfer Learning

Cunli Mao,Zhibo Man,Zhengtao Yu,Xia Wu,Haoyuan Liang 한국정보처리학회 2022 Journal of information processing systems Vol.18 No.4

Using a rich resource language to classify sentiments in a language with few resources is a popular subject ofresearch in natural language processing. Burmese is a low-resource language. In light of the scarcity of labeledtraining data for sentiment classification in Burmese, in this study, we propose a method of transfer learningfor sentiment analysis of a language that uses the feature transfer technique on sentiments in English. Thismethod generates a cross-language word-embedding representation of Burmese vocabulary to map Burmesetext to the semantic space of English text. A model to classify sentiments in English is then pre-trained using aconvolutional neural network and an attention mechanism, where the network shares the model for sentimentanalysis of English. The parameters of the network layer are used to learn the cross-language features of thesentiments, which are then transferred to the model to classify sentiments in Burmese. Finally, the model wastuned using the labeled Burmese data. The results of the experiments show that the proposed method cansignificantly improve the classification of sentiments in Burmese compared to a model trained using only aBurmese corpus.

A Method of Chinese and Thai Cross-Lingual Query Expansion Based on Comparable Corpus

( Peili Tang ),( Jing Zhao ),( Zhengtao Yu ),( Zhuo Wang ),( Yantuan Xian ) 한국정보처리학회 2017 Journal of information processing systems Vol.13 No.4

Cross-lingual query expansion is usually based on the relationship among monolingual words. Bilingual comparable corpus contains relationships among bilingual words. Therefore, this paper proposes a method based on these relationships to conduct query expansion. First, the word vectors which characterize the bilingual words are trained using Chinese and Thai bilingual comparable corpus. Then, the correlation between Chinese query words and Thai words are computed based on these word vectors, followed with selecting the Thai candidate expansion terms via the correlative value. Then, multi-group Thai query expansion sentences are built by the Thai candidate expansion words based on Chinese query sentence. Finally, we can get the optimal sentence using the Chinese and Thai query expansion method, and perform the Thai query expansion. Experiment results show that the cross-lingual query expansion method we proposed can effectively improve the accuracy of Chinese and Thai cross-language information retrieval.

Aspect-Based Sentiment Analysis with Position Embedding Interactive Attention Network

Yan Xiang,Jiqun Zhang,Zhoubin Zhang,Zhengtao Yu,Yantuan Xian 한국정보처리학회 2022 Journal of information processing systems Vol.18 No.5

Aspect-based sentiment analysis is to discover the sentiment polarity towards an aspect from user-generatednatural language. So far, most of the methods only use the implicit position information of the aspect in thecontext, instead of directly utilizing the position relationship between the aspect and the sentiment terms. Infact, neighboring words of the aspect terms should be given more attention than other words in the context. This paper studies the influence of different position embedding methods on the sentimental polarities of givenaspects, and proposes a position embedding interactive attention network based on a long short-term memorynetwork. Firstly, it uses the position information of the context simultaneously in the input layer and theattention layer. Secondly, it mines the importance of different context words for the aspect with the interactiveattention mechanism. Finally, it generates a valid representation of the aspect and the context for sentimentclassification. The model which has been posed was evaluated on the datasets of the Semantic Evaluation 2014. Compared with other baseline models, the accuracy of our model increases by about 2% on the restaurantdataset and 1% on the laptop dataset.